demo_learn
Converts a screen recording into a draft workflow skill by extracting frames, reading on-screen text with OCR or a local vision model, and turning unclear steps into questions to answer.
Instructions
Learn a workflow from a screen recording and turn it into a skill DRAFT.
Frames are extracted (ffmpeg/opencv if installed), the screen text is read with OCR - or, when no OCR engine is installed, described by a LOCAL vision model - changed frames become steps, and the unclear parts become questions for you. The result is a draft, not a verified skill - answer the questions first.
video_path may also be a FOLDER of images (PNG/JPG): extract the frames yourself and hand the folder over - no decoder needed.
Blocked honestly when there is neither a decoder (or a folder), nor an OCR engine, nor a local vision model.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"video_path": "<video_path>"
},
"name": "demo_learn"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | ||
| max_frames | No | ||
| video_path | Yes |